| Popis: |
A facial expression is a natural reflection of human feelings, It is the nature of the human to reciprocate through the facial expression to the living world from where the inputs are perceived. The human science measures the emotion, feeling and sentiment by seeing the human face and face curves, but the recognition of emotion through artificial means with high accuracy and less computing resources is more challenging. In this research work, we developed a state-of-the-art procedure that recognizes the emotion of seven categories, namely Happy, Anger, Sad, Disgust, Neutral, Surprise, and Fear efficiently using deep learning. In this work, the model is trained using the fer2013 data set consists of 35887, and the CK48+ dataset consists of 3540 images. We proposed a hybrid model of feature selection that is used before feeding to the proposed computing model of CNN architecture. We claim through the use of both the models one after the other the emotions is correctly recognized with high accuracy during both training and testing phases, which the conventional method doesn’t have. |
